Effects of Decision Complexity in Goal seeking Gridworlds: A Comparison of Instance Based Learning and Reinforcement Learning Agents

Abstract

Decisions under uncertainty are often made by weighing the expected costs and benefits of the available options. The costs benefits tradeoffs may make decisions easy or difficult, particularly given uncertainty of these costs and rewards. In this research, we evaluate how a cognitive model based on Instance Based Learning Theory (IBLT) and two well-known reinforcement learning (RL) algorithms learn to make better choices in a goal-seeking gridworld task under uncertainty and on increasing degrees of decision complexity. We also use a randomagent as a base level comparison. Our results suggest that IBL and RL models are comparable in their accuracy levels on simple settings, although the RL models are more efficient than the IBL model. However, as decision complexity increases, the IBL model is not only more accurate but also more efficient than the RL models. Our results suggest that the IBL model is able to pursue highly rewarding targets even when the costs increase; while the RL models seem to get distracted by lower costs, reaching lower reward targets.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2020
Accession Number
AD1130203

Entities

People

  • Cleotilde Gonzalez
  • Thuy N. Nguyen

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy
  • Engineered Resilient Systems
  • Human Systems

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Artificial Intelligence
  • Cognitive Science
  • Efficiency
  • Environment
  • Equations
  • Feedback
  • Fungi
  • Gaussian Noise
  • Human Behavior
  • Information Processing
  • Information Systems
  • Judgment
  • Learning
  • Motion Planning
  • Navigation
  • Organization Theory
  • Psychology
  • Reinforcement Learning
  • Uncertainty

Fields of Study

  • Computer science

Readers

  • Life Cycle Cost Analysis
  • Neural Network Machine Learning.
  • STEM Education

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference